Compare commits

..
16 changed files with 4217 additions and 0 deletions
@@ -0,0 +1,427 @@
"""Owner-controlled, CAS-bound retry extension for exhausted Online Agent Tasks."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timezone
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import os
from pathlib import Path
import re
import sqlite3
from typing import Any, Mapping
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
MAX_BODY = 64 * 1024
AUTHORIZE_EXTENSION_ID_ENV = "AIOS_AGENT_TASK_AUTHORIZATION_ID"
class RetryExtensionError(RuntimeError):
def __init__(self, code: str, status: int = 409) -> None:
super().__init__(code)
self.code = code
self.status = status
def _canonical(value: object) -> bytes:
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
def _sha(value: object) -> str:
return hashlib.sha256(_canonical(value)).hexdigest()
def _required_authorization_id() -> str:
value = os.environ.get(AUTHORIZE_EXTENSION_ID_ENV, "").strip()
if not value:
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_MISSING")
if KEY_RE.fullmatch(value) is None:
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_INVALID")
return value
def _now() -> str:
return datetime.now(timezone.utc).isoformat()
def _require_string(value: object, code: str, pattern: re.Pattern[str] | None = None) -> str:
if not isinstance(value, str) or not value.strip():
raise RetryExtensionError(code, 400)
value = value.strip()
if pattern is not None and pattern.fullmatch(value) is None:
raise RetryExtensionError(code, 400)
return value
@dataclass(frozen=True)
class RetryExtensionRequest:
expected_status: str
expected_revision: int
expected_attempt: int
expected_max_attempts: int
next_max_attempts: int
previous_verification_sha256: str
authorization_id: str
idempotency_key: str
@classmethod
def from_mapping(cls, value: Mapping[str, Any]) -> "RetryExtensionRequest":
allowed = {
"expected_status", "expected_revision", "expected_attempt", "expected_max_attempts",
"next_max_attempts", "previous_verification_sha256", "authorization_id", "idempotency_key",
}
if set(value) != allowed:
raise RetryExtensionError("RETRY_EXTENSION_FIELDS_INVALID", 400)
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
if status != "FAILED":
raise RetryExtensionError("EXPECTED_STATUS_INVALID", 400)
ints: dict[str, int] = {}
for field in ("expected_revision", "expected_attempt", "expected_max_attempts", "next_max_attempts"):
item = value[field]
if not isinstance(item, int) or isinstance(item, bool) or item < 0:
raise RetryExtensionError("RETRY_EXTENSION_INTEGER_INVALID", 400)
ints[field] = item
if ints["expected_attempt"] != ints["expected_max_attempts"]:
raise RetryExtensionError("RETRY_EXTENSION_NOT_EXHAUSTED", 409)
if ints["next_max_attempts"] != ints["expected_max_attempts"] + 1:
raise RetryExtensionError("RETRY_EXTENSION_MUST_BE_BOUNDED_ONE_STEP", 400)
if ints["next_max_attempts"] > 50:
raise RetryExtensionError("RETRY_EXTENSION_LIMIT_EXCEEDED", 400)
verification = _require_string(value["previous_verification_sha256"], "VERIFICATION_SHA256_INVALID")
if re.fullmatch(r"[0-9a-f]{64}", verification) is None:
raise RetryExtensionError("VERIFICATION_SHA256_INVALID", 400)
authorization = _require_string(value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE)
key = _require_string(value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE)
return cls(
status,
ints["expected_revision"],
ints["expected_attempt"],
ints["expected_max_attempts"],
ints["next_max_attempts"],
verification,
authorization,
key,
)
def public(self) -> dict[str, Any]:
return {
"expected_status": self.expected_status,
"expected_revision": self.expected_revision,
"expected_attempt": self.expected_attempt,
"expected_max_attempts": self.expected_max_attempts,
"next_max_attempts": self.next_max_attempts,
"previous_verification_sha256": self.previous_verification_sha256,
"authorization_id": self.authorization_id,
"idempotency_key": self.idempotency_key,
}
class RetryExtensionStore:
"""Owns the official mutation. Direct/manual DB edits remain forbidden."""
def __init__(self, db_path: Path) -> None:
self.db_path = Path(db_path)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(self.db_path, timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA foreign_keys=ON")
connection.execute("PRAGMA busy_timeout=30000")
return connection
@staticmethod
def _columns(connection: sqlite3.Connection, table: str) -> dict[str, sqlite3.Row]:
return {str(row["name"]): row for row in connection.execute(f'PRAGMA table_info("{table}")')}
@staticmethod
def _event_table(connection: sqlite3.Connection) -> tuple[str, dict[str, sqlite3.Row]]:
tables = {
row["name"]
for row in connection.execute("SELECT name FROM sqlite_master WHERE type='table'")
}
for name in ("task_events", "events"):
if name not in tables:
continue
columns = RetryExtensionStore._columns(connection, name)
if "task_id" in columns and ("event_type" in columns or "type" in columns):
return name, columns
raise RetryExtensionError("TASK_EVENT_TABLE_UNSUPPORTED", 503)
@staticmethod
def _verification_hash(raw: object) -> str:
if raw in (None, ""):
value: object = {}
elif isinstance(raw, str):
try:
value = json.loads(raw)
except json.JSONDecodeError as exc:
raise RetryExtensionError("TASK_VERIFICATION_INVALID", 409) from exc
else:
value = raw
return _sha(value)
@staticmethod
def _ensure_extension_table(connection: sqlite3.Connection) -> None:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS task_retry_extensions (
task_id TEXT NOT NULL,
idempotency_key TEXT NOT NULL,
request_sha256 TEXT NOT NULL,
authorization_id TEXT NOT NULL,
previous_verification_sha256 TEXT NOT NULL,
previous_max_attempts INTEGER NOT NULL,
next_max_attempts INTEGER NOT NULL,
expected_revision INTEGER NOT NULL,
applied_revision INTEGER NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(task_id, idempotency_key)
)
"""
)
@staticmethod
def _insert_event(
connection: sqlite3.Connection,
task_id: str,
payload: Mapping[str, Any],
) -> None:
table, columns = RetryExtensionStore._event_table(connection)
values: dict[str, Any] = {"task_id": task_id}
if "event_type" in columns:
values["event_type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
else:
values["type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
payload_text = json.dumps(payload, sort_keys=True, separators=(",", ":"))
if "payload_json" in columns:
values["payload_json"] = payload_text
elif "payload" in columns:
values["payload"] = payload_text
else:
raise RetryExtensionError("TASK_EVENT_PAYLOAD_UNSUPPORTED", 503)
if "created_at" in columns:
values["created_at"] = _now()
if "agent_id" in columns:
values["agent_id"] = "owner-control"
if "actor_id" in columns:
values["actor_id"] = "owner-control"
names = list(values)
sql = f'INSERT INTO "{table}" ({",".join(f"""\"{name}\"""" for name in names)}) VALUES ({",".join("?" for _ in names)})'
connection.execute(sql, tuple(values[name] for name in names))
def extend(self, task_id: str, request: RetryExtensionRequest) -> dict[str, Any]:
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
required_authorization_id = _required_authorization_id()
if request.authorization_id != required_authorization_id:
raise RetryExtensionError("RETRY_EXTENSION_AUTHORIZATION_ID_MISMATCH", 403)
request_payload = request.public()
request_sha = _sha(request_payload)
with self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
self._ensure_extension_table(connection)
replay = connection.execute(
"SELECT * FROM task_retry_extensions WHERE task_id=? AND idempotency_key=?",
(task_id, request.idempotency_key),
).fetchone()
if replay is not None:
if replay["request_sha256"] != request_sha:
raise RetryExtensionError("RETRY_EXTENSION_IDEMPOTENCY_CONFLICT", 409)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": request.expected_attempt,
"max_attempts": int(replay["next_max_attempts"]),
"revision": int(replay["applied_revision"]),
"idempotent": True,
"authorization_id": replay["authorization_id"],
"previous_verification_sha256": replay["previous_verification_sha256"],
}
columns = self._columns(connection, "tasks")
required = {
"task_id", "status", "attempt", "max_attempts", "revision", "claimed_by",
"lease_token_hash", "lease_expires_at", "verification_json",
}
if not required.issubset(columns):
raise RetryExtensionError("TASK_SCHEMA_RETRY_EXTENSION_UNSUPPORTED", 503)
task = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
if task is None:
raise RetryExtensionError("TASK_NOT_FOUND", 404)
actual_verification_sha = self._verification_hash(task["verification_json"])
if actual_verification_sha != request.previous_verification_sha256:
raise RetryExtensionError("RETRY_EXTENSION_VERIFICATION_DRIFT", 409)
if (
task["status"] != request.expected_status
or int(task["revision"]) != request.expected_revision
or int(task["attempt"]) != request.expected_attempt
or int(task["max_attempts"]) != request.expected_max_attempts
):
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
for lease_field in ("lease_token_hash", "lease_expires_at"):
if lease_field in columns and task[lease_field] not in (None, ""):
raise RetryExtensionError("RETRY_EXTENSION_ACTIVE_LEASE_DENY", 409)
previous_claimed_by = task["claimed_by"]
applied_revision = request.expected_revision + 1
cursor = connection.execute(
"""
UPDATE tasks
SET status='QUEUED', max_attempts=?, revision=?, claimed_by=NULL,
lease_token_hash=NULL, lease_expires_at=NULL
WHERE task_id=? AND status=? AND revision=? AND attempt=? AND max_attempts=?
AND claimed_by IS ?
AND lease_token_hash IS NULL AND lease_expires_at IS NULL
""",
(
request.next_max_attempts,
applied_revision,
task_id,
request.expected_status,
request.expected_revision,
request.expected_attempt,
request.expected_max_attempts,
previous_claimed_by,
),
)
if cursor.rowcount != 1:
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
event_payload = {
"schema": "aios.task-retry-extension.event.v1",
"task_id": task_id,
"authorization_id": request.authorization_id,
"idempotency_key": request.idempotency_key,
"previous_verification_sha256": request.previous_verification_sha256,
"previous_max_attempts": request.expected_max_attempts,
"next_max_attempts": request.next_max_attempts,
"previous_revision": request.expected_revision,
"applied_revision": applied_revision,
"request_sha256": request_sha,
"previous_claimed_by": previous_claimed_by,
"stale_terminal_claim_normalized": previous_claimed_by not in (None, ""),
}
self._insert_event(connection, task_id, event_payload)
connection.execute(
"""
INSERT INTO task_retry_extensions(
task_id,idempotency_key,request_sha256,authorization_id,previous_verification_sha256,
previous_max_attempts,next_max_attempts,expected_revision,applied_revision,created_at
) VALUES (?,?,?,?,?,?,?,?,?,?)
""",
(
task_id,
request.idempotency_key,
request_sha,
request.authorization_id,
request.previous_verification_sha256,
request.expected_max_attempts,
request.next_max_attempts,
request.expected_revision,
applied_revision,
_now(),
),
)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": request.expected_attempt,
"max_attempts": request.next_max_attempts,
"revision": applied_revision,
"idempotent": False,
"authorization_id": request.authorization_id,
"previous_verification_sha256": request.previous_verification_sha256,
}
class RetryExtensionHandler(BaseHTTPRequestHandler):
store: RetryExtensionStore | None = None
control_token: str = ""
def log_message(self, *_args: Any) -> None:
return
def _json(self, value: Mapping[str, Any], status: int) -> None:
data = json.dumps(dict(value), sort_keys=True, separators=(",", ":")).encode("utf-8")
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(data)))
self.end_headers()
self.wfile.write(data)
def _authorized(self) -> bool:
header = self.headers.get("Authorization", "")
return (
header.startswith("Bearer ")
and bool(self.control_token)
and hmac.compare_digest(header[7:], self.control_token)
)
def do_GET(self) -> None:
if self.path == "/health":
self._json({"status": "ok", "service": "aios-agent-task-retry-extension"}, 200)
else:
self._json({"error": "NOT_FOUND"}, 404)
def do_POST(self) -> None:
match = re.fullmatch(r"/v1/tasks/([^/]+)/retry-extension", self.path)
if match is None:
self._json({"error": "NOT_FOUND"}, 404)
return
if not self._authorized():
self._json({"error": "UNAUTHORIZED"}, 401)
return
try:
length = int(self.headers.get("Content-Length", "0"))
except ValueError:
self._json({"error": "CONTENT_LENGTH_INVALID"}, 400)
return
if length < 1 or length > MAX_BODY:
self._json({"error": "REQUEST_SIZE_INVALID"}, 413)
return
try:
value = json.loads(self.rfile.read(length).decode("utf-8"))
if not isinstance(value, Mapping):
raise ValueError
request = RetryExtensionRequest.from_mapping(value)
if self.store is None:
raise RetryExtensionError("RUNTIME_UNAVAILABLE", 503)
result = self.store.extend(match.group(1), request)
self._json(result, 200 if result["idempotent"] else 201)
except RetryExtensionError as exc:
self._json({"error": exc.code}, exc.status)
except (UnicodeDecodeError, json.JSONDecodeError, ValueError):
self._json({"error": "REQUEST_INVALID"}, 400)
def load_control_token(path: Path) -> str:
if path.is_symlink() or not path.is_file():
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_UNAVAILABLE")
value = path.read_text(encoding="utf-8").strip()
if len(value) < 32:
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_INVALID")
return value
def serve() -> None:
db = Path(os.environ.get("AIOS_AGENT_TASK_DB", "/var/lib/aios-agent-task/state.sqlite3"))
_required_authorization_id()
token_path = Path(
os.environ.get(
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
str(Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials")) / "agent_task_control_token"),
)
)
host = os.environ.get("AIOS_TASK_RETRY_HOST", "127.0.0.1")
port = int(os.environ.get("AIOS_TASK_RETRY_PORT", "18941"))
RetryExtensionHandler.store = RetryExtensionStore(db)
RetryExtensionHandler.control_token = load_control_token(token_path)
ThreadingHTTPServer((host, port), RetryExtensionHandler).serve_forever()
if __name__ == "__main__":
serve()
@@ -0,0 +1,306 @@
"""Uncredentialed deterministic executor for governed Online Agent changes.
This process never receives Agent/Owner/Bridge credentials and never writes Git refs.
It operates only on an exchange bundle and returns hash-bound changed files + test evidence.
"""
from __future__ import annotations
import base64
from dataclasses import dataclass
import errno
import hashlib
import io
import json
import os
from pathlib import Path
import re
import shutil
import socket
import subprocess
import tarfile
import tempfile
import time
from typing import Any, Mapping, Sequence
ALLOWED_PROGRAMS = {"/usr/bin/python3", "/usr/bin/git", "/bin/true", "/usr/bin/true"}
MAX_ARCHIVE_BYTES = 64 * 1024 * 1024
MAX_FILE_BYTES = 4 * 1024 * 1024
SECRET_ENV_TOKENS = ("TOKEN", "SECRET", "PASSWORD", "CREDENTIAL", "AUTHORIZATION", "PRIVATE_KEY")
REQUEST_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{15,254}$")
SENSITIVE_VALUE_RE = re.compile(
r"(?i)(authorization\s*[:=]\s*bearer\s+\S+|authorization\s+bearer\s+\S+|"
r"(?:password|passwd|secret|token|api[_-]?key)\s*[:=]\s*\S+)"
)
class IsolatedExecutorError(RuntimeError):
pass
def sha256(data: bytes) -> str:
return hashlib.sha256(data).hexdigest()
def canonical(value: object) -> bytes:
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
def safe_relative(value: object) -> str:
if not isinstance(value, str) or not value or value.startswith("/"):
raise IsolatedExecutorError("PATH_INVALID")
path = Path(value)
if ".." in path.parts or "." in path.parts or any(part in {"", ".git"} for part in path.parts):
raise IsolatedExecutorError("PATH_INVALID")
return path.as_posix()
def resolve_under(root: Path, relative: str) -> Path:
root = root.resolve()
path = (root / safe_relative(relative)).resolve(strict=False)
if path == root or root not in path.parents:
raise IsolatedExecutorError("PATH_ESCAPE")
return path
def _credential_exposure(directory: Path) -> str | None:
"""Return an exposure code; EACCES is the intended credential isolation proof."""
try:
if not directory.exists():
return None
if directory.is_symlink():
return "CREDENTIAL_MOUNT_SYMLINK"
if os.access(directory, os.R_OK):
return "CREDENTIAL_MOUNT_ACCESSIBLE"
if directory.is_dir():
for child in directory.iterdir():
if child.is_file() and os.access(child, os.R_OK):
return "CREDENTIAL_FILE_ACCESSIBLE"
except PermissionError:
return None
return None
def assert_uncredentialed() -> None:
credentials = Path("/run/credentials")
candidates = {credentials}
credentials_directory = Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
candidates.add(credentials_directory)
leaked = sorted(
key for key, value in os.environ.items()
if value
and (any(token in key.upper() for token in SECRET_ENV_TOKENS) or SENSITIVE_VALUE_RE.search(str(value)))
)
if leaked:
raise IsolatedExecutorError("CREDENTIAL_ENV_EXPOSED:" + ",".join(leaked))
for directory in candidates:
exposure = _credential_exposure(directory)
if exposure is not None:
raise IsolatedExecutorError(exposure)
# In the intended PrivateNetwork namespace host loopback services are unreachable.
try:
probe = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
except OSError as exc:
if exc.errno in {errno.EACCES, errno.EPERM, errno.EAFNOSUPPORT}:
return
raise IsolatedExecutorError("NETWORK_ISOLATION_PROBE_FAILED") from exc
probe.settimeout(0.15)
try:
if probe.connect_ex(("127.0.0.1", 18892)) == 0:
raise IsolatedExecutorError("GOVERNED_BRIDGE_REACHABLE")
finally:
probe.close()
def extract_source(archive: Path, root: Path) -> None:
if archive.is_symlink() or not archive.is_file() or archive.stat().st_size > MAX_ARCHIVE_BYTES:
raise IsolatedExecutorError("SOURCE_ARCHIVE_INVALID")
with tarfile.open(archive, "r:gz") as tf:
for member in tf.getmembers():
path = Path(member.name)
if path.is_absolute() or ".." in path.parts or ".git" in path.parts:
raise IsolatedExecutorError("SOURCE_ARCHIVE_PATH_INVALID")
if member.issym() or member.islnk():
raise IsolatedExecutorError("SOURCE_ARCHIVE_LINK_DENY")
tf.extractall(root, filter="data")
def run_command(item: Mapping[str, Any], root: Path) -> dict[str, Any]:
argv = item.get("argv")
if not isinstance(argv, Sequence) or isinstance(argv, (str, bytes)) or not argv:
raise IsolatedExecutorError("COMMAND_INVALID")
argv = [str(part) for part in argv]
if argv[0] not in ALLOWED_PROGRAMS:
raise IsolatedExecutorError("COMMAND_PROGRAM_DENY")
if argv[0] == "/usr/bin/python3" and "-m" in argv:
index = argv.index("-m")
if index + 1 >= len(argv) or argv[index + 1] not in {"pytest", "py_compile"}:
raise IsolatedExecutorError("PYTHON_MODULE_DENY")
if argv[0] == "/usr/bin/git" and any(
token in {"push", "update-ref", "commit", "merge", "rebase", "reset", "clean", "branch"}
for token in argv[1:]
):
raise IsolatedExecutorError("GIT_MUTATION_DENY")
timeout = int(item.get("timeout_seconds") or 300)
if not 1 <= timeout <= 1800:
raise IsolatedExecutorError("COMMAND_TIMEOUT_INVALID")
cwd = root if item.get("cwd", ".") == "." else resolve_under(root, str(item.get("cwd")))
started = time.monotonic()
completed = subprocess.run(
argv,
cwd=cwd,
capture_output=True,
text=True,
check=False,
timeout=timeout,
env={"PATH": "/usr/bin:/bin", "LC_ALL": "C.UTF-8"},
)
result = {
"label": str(item.get("label") or "command"),
"exit_code": completed.returncode,
"stdout_sha256": sha256(completed.stdout.encode("utf-8", "replace")),
"stderr_sha256": sha256(completed.stderr.encode("utf-8", "replace")),
"duration_ms": int((time.monotonic() - started) * 1000),
}
if completed.returncode != 0:
raise IsolatedExecutorError(
"COMMAND_FAILED:" + result["label"] + ":" + str(completed.returncode)
)
return result
def apply_changes(request: Mapping[str, Any], root: Path) -> list[str]:
changes = request.get("change_set")
if not isinstance(changes, list) or not changes:
raise IsolatedExecutorError("CHANGE_SET_INVALID")
changed: list[str] = []
for change in changes:
if not isinstance(change, Mapping):
raise IsolatedExecutorError("CHANGE_INVALID")
relative = safe_relative(change.get("path"))
path = resolve_under(root, relative)
current = path.read_bytes() if path.is_file() else None
expected = change.get("expected_sha256")
if expected is not None and (current is None or sha256(current) != expected):
raise IsolatedExecutorError("SOURCE_DRIFT:" + relative)
operation = change.get("operation")
if operation == "write_file":
content = change.get("content")
if not isinstance(content, str):
raise IsolatedExecutorError("WRITE_CONTENT_INVALID")
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(content, encoding="utf-8")
elif operation == "replace_text":
if current is None:
raise IsolatedExecutorError("REPLACE_SOURCE_MISSING")
old = str(change.get("old"))
new = str(change.get("new"))
count = int(change.get("count", 1))
text = current.decode("utf-8")
if text.count(old) != count:
raise IsolatedExecutorError("REPLACE_COUNT_INVALID:" + relative)
path.write_text(text.replace(old, new), encoding="utf-8")
elif operation == "delete_file":
if path.exists():
path.unlink()
else:
raise IsolatedExecutorError("CHANGE_OPERATION_INVALID")
changed.append(relative)
return sorted(set(changed))
def changed_bundle(root: Path, changed: list[str]) -> list[dict[str, Any]]:
files = []
for relative in changed:
path = resolve_under(root, relative)
if path.exists():
data = path.read_bytes()
if len(data) > MAX_FILE_BYTES:
raise IsolatedExecutorError("CHANGED_FILE_TOO_LARGE:" + relative)
files.append({
"path": relative,
"deleted": False,
"sha256": sha256(data),
"content_b64": base64.b64encode(data).decode("ascii"),
})
else:
files.append({"path": relative, "deleted": True, "sha256": None, "content_b64": None})
return files
def execute_request(request_path: Path, result_path: Path) -> None:
assert_uncredentialed()
request = json.loads(request_path.read_text(encoding="utf-8"))
if request.get("schema") != "aios.isolated-execution.request.v1":
raise IsolatedExecutorError("REQUEST_SCHEMA_INVALID")
request_id = request.get("request_id")
if not isinstance(request_id, str) or not REQUEST_ID_RE.fullmatch(request_id):
raise IsolatedExecutorError("REQUEST_ID_INVALID")
source_archive = Path(str(request.get("source_archive") or ""))
if not source_archive.is_absolute():
raise IsolatedExecutorError("SOURCE_ARCHIVE_PATH_INVALID")
expected_archive_sha = str(request.get("source_archive_sha256") or "")
if sha256(source_archive.read_bytes()) != expected_archive_sha:
raise IsolatedExecutorError("SOURCE_ARCHIVE_SHA_MISMATCH")
with tempfile.TemporaryDirectory(prefix="aios-isolated-executor-") as temporary:
root = Path(temporary) / "workspace"
root.mkdir()
extract_source(source_archive, root)
changed = apply_changes(request, root)
commands = [
run_command(item, root)
for item in request.get("verification", [])
if isinstance(item, Mapping)
]
result = {
"schema": "aios.isolated-execution.result.v1",
"request_id": request_id,
"request_sha256": sha256(canonical(request)),
"changed_files": changed_bundle(root, changed),
"verification": commands,
"credential_isolation": {
"credential_env_absent": True,
"credential_mount_inaccessible": True,
"governed_bridge_unreachable": True,
},
}
result["result_sha256"] = sha256(canonical(result))
temporary_result = result_path.with_suffix(".tmp")
temporary_result.write_text(json.dumps(result, sort_keys=True, separators=(",", ":")), encoding="utf-8")
os.replace(temporary_result, result_path)
def serve(root: Path) -> None:
assert_uncredentialed()
requests = root / "requests"
results = root / "results"
failed = root / "failed"
for path in (requests, results, failed):
path.mkdir(parents=True, exist_ok=True)
while True:
for request in sorted(requests.glob("*.json")):
if request.is_symlink():
continue
result = results / request.name
try:
execute_request(request, result)
request.unlink()
except Exception as exc:
(failed / request.name).write_text(
json.dumps({"error": str(exc) or type(exc).__name__}, sort_keys=True),
encoding="utf-8",
)
request.unlink(missing_ok=True)
time.sleep(0.5)
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--root", default="/var/lib/aios-online-agent-executor")
parser.add_argument("--request")
parser.add_argument("--result")
args = parser.parse_args()
if args.request and args.result:
execute_request(Path(args.request), Path(args.result))
else:
serve(Path(args.root))
@@ -0,0 +1,301 @@
"""Durable checkpoint journal for the generic Online Agent worker.
The JSON task state remains a fast cache. This SQLite journal is the durable,
append-only evidence used for restart/resume/replay decisions.
"""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timezone
import hashlib
import json
from pathlib import Path
import sqlite3
from typing import Any, Mapping
PHASE_ORDER = {
"claimed": 10,
"workspace_prepared": 20,
"verification_passed": 30,
"source_capture_done": 40,
"commit_done": 40,
"reconciliation_required": 45,
"result_pending": 50,
"result_submitted": 60,
}
class CheckpointError(RuntimeError):
pass
def canonical(value: object) -> bytes:
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False, default=str).encode("utf-8")
def sha256_json(value: object) -> str:
return hashlib.sha256(canonical(value)).hexdigest()
def now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class CheckpointBinding:
task_id: str
attempt: int
execution_digest: str
job_id: str
repository: str
base_oid: str
expected_branch_oid: str
target_branch: str
generation: int
def material(self) -> dict[str, Any]:
return {
"task_id": self.task_id,
"attempt": self.attempt,
"execution_digest": self.execution_digest,
"job_id": self.job_id,
"repository": self.repository,
"base_oid": self.base_oid,
"expected_branch_oid": self.expected_branch_oid,
"target_branch": self.target_branch,
"generation": self.generation,
}
@property
def binding_sha256(self) -> str:
return sha256_json(self.material())
class CheckpointStore:
def __init__(self, path: Path) -> None:
self.path = Path(path)
self.path.parent.mkdir(parents=True, exist_ok=True)
with self._connect() as connection:
connection.executescript(
"""
CREATE TABLE IF NOT EXISTS checkpoints(
task_id TEXT NOT NULL,
attempt INTEGER NOT NULL,
sequence INTEGER NOT NULL,
phase TEXT NOT NULL,
phase_order INTEGER NOT NULL,
execution_digest TEXT NOT NULL,
job_id TEXT NOT NULL,
repository TEXT NOT NULL,
base_oid TEXT NOT NULL,
expected_branch_oid TEXT NOT NULL,
target_branch TEXT NOT NULL,
generation INTEGER NOT NULL,
binding_sha256 TEXT NOT NULL,
payload_json TEXT NOT NULL,
payload_sha256 TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(task_id, attempt, sequence)
);
CREATE INDEX IF NOT EXISTS idx_checkpoints_task_latest
ON checkpoints(task_id, attempt DESC, sequence DESC);
CREATE UNIQUE INDEX IF NOT EXISTS idx_checkpoints_exact_replay
ON checkpoints(task_id, attempt, phase, payload_sha256);
CREATE TABLE IF NOT EXISTS checkpoint_heads(
task_id TEXT PRIMARY KEY,
attempt INTEGER NOT NULL,
sequence INTEGER NOT NULL,
phase TEXT NOT NULL,
phase_order INTEGER NOT NULL,
execution_digest TEXT NOT NULL,
binding_sha256 TEXT NOT NULL,
payload_sha256 TEXT NOT NULL,
updated_at TEXT NOT NULL
);
"""
)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(self.path, timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA foreign_keys=ON")
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
connection.execute("PRAGMA busy_timeout=30000")
return connection
@staticmethod
def _phase_order(phase: str) -> int:
try:
return PHASE_ORDER[phase]
except KeyError as exc:
raise CheckpointError("CHECKPOINT_PHASE_INVALID") from exc
def append(
self,
binding: CheckpointBinding,
phase: str,
payload: Mapping[str, Any],
) -> dict[str, Any]:
order = self._phase_order(phase)
payload_value = dict(payload)
payload_sha = sha256_json(payload_value)
with self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
replay = connection.execute(
"""
SELECT * FROM checkpoints
WHERE task_id=? AND attempt=? AND phase=? AND payload_sha256=?
""",
(binding.task_id, binding.attempt, phase, payload_sha),
).fetchone()
if replay is not None:
connection.commit()
return dict(replay)
head = connection.execute(
"SELECT * FROM checkpoint_heads WHERE task_id=?",
(binding.task_id,),
).fetchone()
if head is not None:
head_attempt = int(head["attempt"])
head_order = int(head["phase_order"])
if binding.attempt < head_attempt:
raise CheckpointError("CHECKPOINT_ATTEMPT_REGRESSION")
if binding.attempt == head_attempt:
if head["execution_digest"] != binding.execution_digest:
raise CheckpointError("CHECKPOINT_EXECUTION_DIGEST_CONFLICT")
if head["binding_sha256"] != binding.binding_sha256:
raise CheckpointError("CHECKPOINT_SCOPE_MISMATCH_DENY")
if order < head_order and phase != "reconciliation_required":
raise CheckpointError("CHECKPOINT_PHASE_REGRESSION")
sequence = int(head["sequence"]) + 1
else:
sequence = 1
else:
sequence = 1
created_at = now()
connection.execute(
"""
INSERT INTO checkpoints(
task_id,attempt,sequence,phase,phase_order,execution_digest,job_id,
repository,base_oid,expected_branch_oid,target_branch,generation,
binding_sha256,payload_json,payload_sha256,created_at
) VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)
""",
(
binding.task_id,
binding.attempt,
sequence,
phase,
order,
binding.execution_digest,
binding.job_id,
binding.repository,
binding.base_oid,
binding.expected_branch_oid,
binding.target_branch,
binding.generation,
binding.binding_sha256,
canonical(payload_value).decode("utf-8"),
payload_sha,
created_at,
),
)
connection.execute(
"""
INSERT INTO checkpoint_heads(
task_id,attempt,sequence,phase,phase_order,execution_digest,
binding_sha256,payload_sha256,updated_at
) VALUES (?,?,?,?,?,?,?,?,?)
ON CONFLICT(task_id) DO UPDATE SET
attempt=excluded.attempt,
sequence=excluded.sequence,
phase=excluded.phase,
phase_order=excluded.phase_order,
execution_digest=excluded.execution_digest,
binding_sha256=excluded.binding_sha256,
payload_sha256=excluded.payload_sha256,
updated_at=excluded.updated_at
""",
(
binding.task_id,
binding.attempt,
sequence,
phase,
order,
binding.execution_digest,
binding.binding_sha256,
payload_sha,
created_at,
),
)
connection.commit()
row = connection.execute(
"SELECT * FROM checkpoints WHERE task_id=? AND attempt=? AND sequence=?",
(binding.task_id, binding.attempt, sequence),
).fetchone()
return dict(row)
def latest(self, task_id: str) -> dict[str, Any] | None:
with self._connect() as connection:
row = connection.execute(
"""
SELECT * FROM checkpoints
WHERE task_id=?
ORDER BY attempt DESC, sequence DESC
LIMIT 1
""",
(task_id,),
).fetchone()
if row is None:
return None
value = dict(row)
value["payload"] = json.loads(value.pop("payload_json"))
return value
def latest_for_attempt(self, task_id: str, attempt: int) -> dict[str, Any] | None:
with self._connect() as connection:
row = connection.execute(
"""
SELECT * FROM checkpoints
WHERE task_id=? AND attempt=?
ORDER BY sequence DESC
LIMIT 1
""",
(task_id, attempt),
).fetchone()
if row is None:
return None
value = dict(row)
value["payload"] = json.loads(value.pop("payload_json"))
return value
def verify_latest_binding(self, binding: CheckpointBinding) -> dict[str, Any] | None:
value = self.latest(binding.task_id)
if value is None:
return None
if int(value["attempt"]) > binding.attempt:
raise CheckpointError("CHECKPOINT_FUTURE_ATTEMPT")
# A previous attempt may be reused only when the immutable execution/scope binding matches.
if value["execution_digest"] != binding.execution_digest:
return None
expected = CheckpointBinding(
task_id=value["task_id"],
attempt=int(value["attempt"]),
execution_digest=value["execution_digest"],
job_id=value["job_id"],
repository=value["repository"],
base_oid=value["base_oid"],
expected_branch_oid=value["expected_branch_oid"],
target_branch=value["target_branch"],
generation=int(value["generation"]),
)
current_scope = binding.material()
historical_scope = expected.material()
current_scope.pop("attempt", None)
historical_scope.pop("attempt", None)
if sha256_json(current_scope) != sha256_json(historical_scope):
raise CheckpointError("CHECKPOINT_SCOPE_MISMATCH_DENY")
return value
@@ -0,0 +1,397 @@
"""Canonical governed execution projection for Online Agent Tasks.
The durable governed binding is authoritative. Natural-language task fields and
worker configuration are never allowed to invent repository, ref, generation, or
idempotency coordinates.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass
import hashlib
import json
import re
from pathlib import Path
from typing import Any, Mapping, Sequence
import urllib.error
import urllib.request
EXECUTION_SCHEMA = "aios.online-agent.execution.v2"
PROJECTION_SCHEMA = "aios.online-agent.task-projection.v1"
OID_RE = re.compile(r"^[0-9a-f]{40}$")
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
BRANCH_RE = re.compile(r"^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$")
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
PROTECTED_PREFIXES = ("main", "master", "refs/", "tags/", "tag/", "release/", "baseline/", "production/")
MUTATION_ACTIONS = frozenset({"deterministic"})
SUPPORTED_ACTIONS = frozenset({"deterministic", "source_capture"})
class ExecutionProjectionError(RuntimeError):
"""A canonical fail-closed projection or validation error."""
class OnlineTaskProjectionClient:
"""Official HTTP projection client using only a control credential reference."""
def __init__(self, api_base: str, control_token_path: Path) -> None:
self.api_base = api_base.rstrip("/")
self.control_token_path = Path(control_token_path)
def _token(self) -> str:
path = self.control_token_path
if path.is_symlink() or not path.is_file():
_error("ONLINE_TASK_PROJECTION_CONTROL_UNAVAILABLE")
value = path.read_text(encoding="utf-8").strip()
if len(value) < 32:
_error("ONLINE_TASK_PROJECTION_CONTROL_INVALID")
return value
def create(
self,
projected_task: Mapping[str, Any],
*,
binding: "GovernedExecutionBinding",
) -> dict[str, Any]:
body = dict(projected_task)
payload = _canonical(body).encode("utf-8")
request = urllib.request.Request(
self.api_base + "/v1/tasks",
method="POST",
data=payload,
headers={
"Authorization": "Bearer " + self._token(),
"Content-Type": "application/json",
"Accept": "application/json",
},
)
try:
with urllib.request.urlopen(request, timeout=15) as response:
result = json.loads(response.read().decode("utf-8"))
status = response.status
except urllib.error.HTTPError as exc:
raw = exc.read(8192).decode("utf-8", "replace")
try:
error = json.loads(raw).get("error")
except (AttributeError, json.JSONDecodeError):
error = "HTTP_ERROR"
raise ExecutionProjectionError(f"ONLINE_TASK_PROJECTION_FAILED:{exc.code}:{error}") from exc
except (OSError, urllib.error.URLError, TimeoutError) as exc:
raise ExecutionProjectionError("ONLINE_TASK_PROJECTION_UNAVAILABLE") from exc
if status not in {200, 201} or not isinstance(result, dict):
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
if result.get("task_id") != binding.task_id or result.get("status") not in {"QUEUED", "VERIFYING", "SUCCEEDED"}:
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
metadata = result.get("metadata")
if not isinstance(metadata, Mapping):
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
returned_execution = validate_execution_envelope(
_object(metadata.get("execution"), "ONLINE_TASK_PROJECTION_RESPONSE_INVALID"),
binding=binding,
)
submitted_metadata = _object(body.get("metadata"), "ONLINE_TASK_PROJECTION_REQUEST_INVALID")
submitted_execution = validate_execution_envelope(
_object(submitted_metadata.get("execution"), "ONLINE_TASK_PROJECTION_REQUEST_INVALID"),
binding=binding,
)
if _canonical(returned_execution) != _canonical(submitted_execution):
_error("ONLINE_TASK_PROJECTION_RESPONSE_BINDING_INVALID")
return result
def _error(code: str) -> None:
raise ExecutionProjectionError(code)
def _object(value: object, code: str) -> dict[str, Any]:
if not isinstance(value, Mapping):
_error(code)
return dict(value)
def _string(value: object, code: str) -> str:
if not isinstance(value, str) or not value.strip():
_error(code)
return value.strip()
def _task_id(value: object) -> str:
value = _string(value, "TASK_ID_INVALID")
if TASK_RE.fullmatch(value) is None:
_error("TASK_ID_INVALID")
return value
def _oid(value: object, code: str) -> str:
value = _string(value, code)
if OID_RE.fullmatch(value) is None:
_error(code)
return value
def _branch(value: object) -> str:
value = _string(value, "TARGET_BRANCH_INVALID")
if BRANCH_RE.fullmatch(value) is None or value.startswith(PROTECTED_PREFIXES):
_error("TARGET_BRANCH_INVALID")
return value
def _generation(value: object) -> int:
if not isinstance(value, int) or isinstance(value, bool) or value < 1:
_error("GENERATION_INVALID")
return value
def _canonical(value: object) -> str:
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
def _digest(value: object) -> str:
return hashlib.sha256(_canonical(value).encode("utf-8")).hexdigest()
def _source_signals(value: object) -> tuple[str, ...]:
"""Normalize untrusted natural-language hints before they enter a signed envelope."""
if value is None:
return ()
if not isinstance(value, Sequence) or isinstance(value, (str, bytes)):
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
result: list[str] = []
for item in value:
if not isinstance(item, str):
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
text = " ".join(item.split()).strip()
if not text:
continue
# Projection may accept long task prose, but execution envelopes stay bounded.
text = text[:512].rstrip()
if text not in result:
result.append(text)
if len(result) == 16:
break
return tuple(result)
def _capabilities(value: object) -> tuple[str, ...]:
if value is None:
return ()
if not isinstance(value, Sequence) or isinstance(value, (str, bytes)):
_error("CAPABILITY_SCOPE_INVALID")
result = tuple(sorted({_string(item, "CAPABILITY_SCOPE_INVALID") for item in value}))
if any(len(item) > 120 for item in result):
_error("CAPABILITY_SCOPE_INVALID")
return result
@dataclass(frozen=True, slots=True)
class GovernedExecutionBinding:
task_id: str
job_id: str
repository: str
base_oid: str
expected_branch_oid: str
target_branch: str
branch_mode: str
generation: int
idempotency_key: str
@classmethod
def from_mapping(cls, value: Mapping[str, Any]) -> "GovernedExecutionBinding":
data = dict(value)
task_id = _task_id(data.get("task_id"))
job_id = _string(data.get("job_id"), "JOB_ID_REQUIRED")
if TASK_RE.fullmatch(job_id) is None:
_error("JOB_ID_INVALID")
repository = _string(data.get("repository"), "REPOSITORY_INVALID")
if repository != "aios/aios":
_error("WRONG_REPOSITORY_ENVELOPE_DENY")
base_oid = _oid(data.get("base_oid"), "BASE_OID_INVALID")
expected = _oid(data.get("expected_branch_oid"), "EXPECTED_BRANCH_OID_INVALID")
target = _branch(data.get("target_branch"))
mode = _string(data.get("branch_mode"), "BRANCH_MODE_MISSING")
if mode not in {"CREATE_NEW", "CONTINUE_EXISTING"}:
_error("BRANCH_MODE_INVALID")
generation = _generation(data.get("generation"))
if mode == "CREATE_NEW" and expected != base_oid:
_error("EXPECTED_BASE_CONFLICT")
key = _string(data.get("idempotency_key"), "IDEMPOTENCY_KEY_INVALID")
if KEY_RE.fullmatch(key) is None:
_error("IDEMPOTENCY_KEY_INVALID")
return cls(task_id, job_id, repository, base_oid, expected, target, mode, generation, key)
def public(self) -> dict[str, Any]:
return asdict(self)
def binding_from_bootstrap(value: Mapping[str, Any]) -> GovernedExecutionBinding:
return GovernedExecutionBinding.from_mapping(value)
def validate_execution_envelope(
value: Mapping[str, Any],
*,
binding: GovernedExecutionBinding | None = None,
worker_capabilities: Sequence[str] | None = None,
) -> dict[str, Any]:
envelope = dict(value)
if envelope.get("schema") != EXECUTION_SCHEMA:
_error("EXECUTION_ENVELOPE_SCHEMA_VALIDATION")
candidate = GovernedExecutionBinding.from_mapping(envelope)
if binding is not None and candidate != binding:
comparisons = (
(candidate.task_id, binding.task_id, "TASK_BINDING_CONFLICT"),
(candidate.job_id, binding.job_id, "JOB_BINDING_CONFLICT"),
(candidate.repository, binding.repository, "WRONG_REPOSITORY_ENVELOPE_DENY"),
(candidate.base_oid, binding.base_oid, "WRONG_BASE_ENVELOPE_DENY"),
(candidate.expected_branch_oid, binding.expected_branch_oid, "WRONG_EXPECTED_HEAD_ENVELOPE_DENY"),
(candidate.target_branch, binding.target_branch, "WRONG_BRANCH_ENVELOPE_DENY"),
(candidate.generation, binding.generation, "WRONG_GENERATION_ENVELOPE_DENY"),
(candidate.branch_mode, binding.branch_mode, "BRANCH_MODE_BINDING_CONFLICT"),
(candidate.idempotency_key, binding.idempotency_key, "IDEMPOTENCY_BINDING_CONFLICT"),
)
for actual, expected, code in comparisons:
if actual != expected:
_error(code)
action = _string(envelope.get("action"), "EXECUTION_ACTION_MISSING")
if action not in SUPPORTED_ACTIONS:
_error("EXECUTION_ACTION_UNSUPPORTED")
capability_scope = _capabilities(envelope.get("capability_scope"))
if worker_capabilities is not None and not set(capability_scope).issubset(set(worker_capabilities)):
_error("CAPABILITY_MISMATCH_DENY")
workspace = _object(envelope.get("workspace"), "WORKSPACE_POLICY_REQUIRED")
if workspace.get("authority_git_dir") != "/data/aios-gitops/repo.git" or workspace.get("read_only_repository") is not True:
_error("WORKSPACE_POLICY_DENY")
governance = _object(envelope.get("governance"), "GOVERNANCE_POLICY_REQUIRED")
governed_coordinates = (
(governance.get("task_id"), candidate.task_id, "TASK_BINDING_CONFLICT"),
(governance.get("job_id"), candidate.job_id, "JOB_BINDING_CONFLICT"),
(governance.get("idempotency_key"), candidate.idempotency_key, "IDEMPOTENCY_BINDING_CONFLICT"),
)
for actual_coordinate, expected_coordinate, code in governed_coordinates:
if actual_coordinate != expected_coordinate:
_error(code)
commit_key = _string(governance.get("commit_idempotency_key"), "COMMIT_IDEMPOTENCY_KEY_INVALID")
if KEY_RE.fullmatch(commit_key) is None:
_error("COMMIT_IDEMPOTENCY_KEY_INVALID")
if governance.get("writer_lease") is not (action in MUTATION_ACTIONS):
_error("WRITER_LEASE_POLICY_DENY")
for field in ("main_write", "production_write", "tag_write", "baseline_write", "force_push", "protected_ref_bypass"):
if governance.get(field, False) is not False:
_error("POLICY_DENY")
changes = envelope.get("change_set")
verification = envelope.get("verification")
if not isinstance(changes, list) or not isinstance(verification, list):
_error("EXECUTION_OPERATIONS_INVALID")
if action == "source_capture":
if changes or verification:
_error("SOURCE_CAPTURE_MUTATION_DENY")
signals = list(_source_signals(envelope.get("source_signals") or []))
if envelope.get("source_signals") != signals:
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
elif not changes:
_error("CHANGE_SET_INVALID")
declared = str(envelope.get("execution_digest") or "")
material = {key: item for key, item in envelope.items() if key != "execution_digest"}
actual = _digest(material)
if declared != actual:
_error("EXECUTION_DIGEST_INVALID")
return {**material, "execution_digest": actual}
def project_execution_envelope(
binding: GovernedExecutionBinding,
execution_request: Mapping[str, Any] | None = None,
*,
required_capabilities: Sequence[str] = (),
) -> dict[str, Any]:
request = dict(execution_request or {})
action = str(request.get("action") or "source_capture")
if action not in SUPPORTED_ACTIONS:
_error("EXECUTION_ACTION_UNSUPPORTED")
capabilities = _capabilities(request.get("capability_scope", required_capabilities))
governance = {
"task_id": binding.task_id,
"job_id": binding.job_id,
"idempotency_key": binding.idempotency_key,
"commit_idempotency_key": str(request.get("commit_idempotency_key") or f"{binding.task_id}-commit-g{binding.generation}"),
"writer_lease": action in MUTATION_ACTIONS,
"main_write": False,
"production_write": False,
"tag_write": False,
"baseline_write": False,
"force_push": False,
"protected_ref_bypass": False,
}
supplied_governance = request.get("governance")
if supplied_governance is not None:
governance.update(_object(supplied_governance, "GOVERNANCE_POLICY_REQUIRED"))
material: dict[str, Any] = {
"schema": EXECUTION_SCHEMA,
**binding.public(),
"action": action,
"adapter": str(request.get("adapter") or ("deterministic" if action == "deterministic" else "source_capture")),
"capability_scope": list(capabilities),
"change_set": list(request.get("change_set") or []),
"verification": list(request.get("verification") or []),
"source_signals": list(_source_signals(request.get("source_signals") or [])) if action == "source_capture" else [],
"governance": governance,
"workspace": {
"authority_git_dir": "/data/aios-gitops/repo.git",
"read_only_repository": True,
"cleanup_policy": "always",
},
}
envelope = {**material, "execution_digest": _digest(material)}
return validate_execution_envelope(envelope, binding=binding)
def project_online_task(
binding: GovernedExecutionBinding,
task_request: Mapping[str, Any],
execution_request: Mapping[str, Any] | None = None,
) -> dict[str, Any]:
request = dict(task_request)
required = _capabilities(request.get("required_capabilities"))
execution = project_execution_envelope(binding, execution_request, required_capabilities=required)
metadata = dict(request.get("metadata") or {})
if "execution" in metadata:
validate_execution_envelope(_object(metadata["execution"], "EXECUTION_ENVELOPE_INVALID"), binding=binding)
if metadata["execution"] != execution:
_error("EXECUTION_PROJECTION_CONFLICT")
metadata["execution"] = execution
metadata["execution_projection"] = {
"schema": PROJECTION_SCHEMA,
"task_id": binding.task_id,
"job_id": binding.job_id,
"execution_digest": execution["execution_digest"],
}
return {
**request,
"task_id": binding.task_id,
"metadata": metadata,
"required_capabilities": list(required),
"idempotency_key": str(request.get("idempotency_key") or f"online-task:{binding.idempotency_key}"),
}
def resolve_task_execution(
task: Mapping[str, Any],
binding: GovernedExecutionBinding,
*,
worker_capabilities: Sequence[str] | None = None,
) -> tuple[dict[str, Any], str]:
metadata = task.get("metadata")
if isinstance(metadata, Mapping) and "execution" in metadata:
value = validate_execution_envelope(
_object(metadata["execution"], "EXECUTION_ENVELOPE_INVALID"),
binding=binding,
worker_capabilities=worker_capabilities,
)
return value, "persisted"
projected = project_execution_envelope(
binding,
{"action": "source_capture", "capability_scope": task.get("required_capabilities") or []},
required_capabilities=task.get("required_capabilities") or [],
)
validate_execution_envelope(projected, binding=binding, worker_capabilities=worker_capabilities)
return projected, "recovered_projection"
@@ -0,0 +1,187 @@
"""Durable, authority-bound deterministic execution plans for Online Agent Tasks."""
from __future__ import annotations
from contextlib import contextmanager
from dataclasses import dataclass
import fcntl
import hashlib
import json
from pathlib import Path
from typing import Any, Mapping
from aios_online_agent_execution import (
GovernedExecutionBinding,
project_execution_envelope,
)
class ExecutionPlanError(RuntimeError):
pass
def _canonical(value: object) -> bytes:
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
def _digest(value: object) -> str:
return hashlib.sha256(_canonical(value)).hexdigest()
def _task_key(task_id: str) -> str:
readable = "".join(ch if ch.isalnum() or ch in "._-" else "-" for ch in task_id).strip("-")[:72] or "task"
return readable + "-" + hashlib.sha256(task_id.encode("utf-8")).hexdigest()[:24]
@dataclass(frozen=True)
class ExecutionPlanRecord:
task_id: str
job_id: str
source_head_oid: str
generation: int
idempotency_key: str
plan_digest: str
execution: dict[str, Any]
def public(self) -> dict[str, Any]:
return {
"schema": "aios.online-agent.plan-record.v1",
"task_id": self.task_id,
"job_id": self.job_id,
"source_head_oid": self.source_head_oid,
"generation": self.generation,
"idempotency_key": self.idempotency_key,
"plan_digest": self.plan_digest,
"execution": dict(self.execution),
}
class ExecutionPlanStore:
def __init__(self, root: Path) -> None:
self.root = Path(root)
self.root.mkdir(parents=True, exist_ok=True)
def _path(self, task_id: str) -> Path:
return self.root / (_task_key(task_id) + ".json")
@contextmanager
def _lock(self, task_id: str):
path = self.root / (_task_key(task_id) + ".lock")
with path.open("a+b") as handle:
fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
try:
yield
finally:
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
@staticmethod
def _source_head(binding: GovernedExecutionBinding) -> str:
return binding.expected_branch_oid if binding.branch_mode == "CONTINUE_EXISTING" else binding.base_oid
def _read(self, task_id: str) -> ExecutionPlanRecord | None:
path = self._path(task_id)
if not path.is_file() or path.is_symlink():
return None
value = json.loads(path.read_text(encoding="utf-8"))
if not isinstance(value, Mapping) or value.get("schema") != "aios.online-agent.plan-record.v1":
raise ExecutionPlanError("EXECUTION_PLAN_RECORD_INVALID")
execution = value.get("execution")
if not isinstance(execution, Mapping):
raise ExecutionPlanError("EXECUTION_PLAN_RECORD_INVALID")
return ExecutionPlanRecord(
task_id=str(value.get("task_id") or ""),
job_id=str(value.get("job_id") or ""),
source_head_oid=str(value.get("source_head_oid") or ""),
generation=int(value.get("generation") or 0),
idempotency_key=str(value.get("idempotency_key") or ""),
plan_digest=str(value.get("plan_digest") or ""),
execution=dict(execution),
)
def register(
self,
binding: GovernedExecutionBinding,
request: Mapping[str, Any],
) -> dict[str, Any]:
with self._lock(binding.task_id):
return self._register_locked(binding, request)
def _register_locked(
self,
binding: GovernedExecutionBinding,
request: Mapping[str, Any],
) -> dict[str, Any]:
if request.get("schema") != "aios.online-agent.plan.v1":
raise ExecutionPlanError("EXECUTION_PLAN_SCHEMA_INVALID")
if request.get("task_id") != binding.task_id or request.get("job_id") != binding.job_id:
raise ExecutionPlanError("EXECUTION_PLAN_BINDING_CONFLICT")
if int(request.get("generation") or 0) != binding.generation:
raise ExecutionPlanError("EXECUTION_PLAN_GENERATION_CONFLICT")
source_head = str(request.get("source_head_oid") or "")
if source_head != self._source_head(binding):
raise ExecutionPlanError("EXECUTION_PLAN_SOURCE_HEAD_CONFLICT")
key = str(request.get("idempotency_key") or "")
if len(key) < 8:
raise ExecutionPlanError("EXECUTION_PLAN_IDEMPOTENCY_INVALID")
execution_request = request.get("execution")
if not isinstance(execution_request, Mapping) or execution_request.get("action") != "deterministic":
raise ExecutionPlanError("EXECUTION_PLAN_DETERMINISTIC_REQUIRED")
envelope = project_execution_envelope(binding, execution_request)
material = {
"task_id": binding.task_id,
"job_id": binding.job_id,
"source_head_oid": source_head,
"generation": binding.generation,
"idempotency_key": key,
"execution": dict(execution_request),
}
plan_digest = _digest(material)
existing = self._read(binding.task_id)
expected_previous = request.get("expected_previous_plan_digest")
if existing is not None:
if existing.idempotency_key == key:
if existing.plan_digest != plan_digest:
raise ExecutionPlanError("EXECUTION_PLAN_IDEMPOTENCY_CONFLICT")
return {**existing.public(), "idempotent": True, "execution_digest": envelope["execution_digest"]}
if expected_previous != existing.plan_digest:
raise ExecutionPlanError("EXECUTION_PLAN_REPLACEMENT_CAS_MISMATCH")
if existing.source_head_oid != source_head:
raise ExecutionPlanError("EXECUTION_PLAN_STALE_REPLACEMENT_DENY")
elif expected_previous not in (None, ""):
raise ExecutionPlanError("EXECUTION_PLAN_REPLACEMENT_CAS_MISMATCH")
record = ExecutionPlanRecord(
task_id=binding.task_id,
job_id=binding.job_id,
source_head_oid=source_head,
generation=binding.generation,
idempotency_key=key,
plan_digest=plan_digest,
execution=dict(execution_request),
)
path = self._path(binding.task_id)
temporary = path.with_suffix(".tmp")
temporary.write_text(
json.dumps(record.public(), sort_keys=True, separators=(",", ":")),
encoding="utf-8",
)
temporary.replace(path)
return {**record.public(), "idempotent": False, "execution_digest": envelope["execution_digest"]}
def resolve(self, binding: GovernedExecutionBinding) -> dict[str, Any] | None:
record = self._read(binding.task_id)
if record is None:
return None
if (
record.task_id != binding.task_id
or record.job_id != binding.job_id
or record.generation != binding.generation
):
raise ExecutionPlanError("EXECUTION_PLAN_BINDING_CONFLICT")
if record.source_head_oid != self._source_head(binding):
raise ExecutionPlanError("EXECUTION_PLAN_SOURCE_HEAD_DRIFT")
envelope = project_execution_envelope(binding, record.execution)
return {
"execution": dict(record.execution),
"plan_digest": record.plan_digest,
"execution_digest": envelope["execution_digest"],
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,36 @@
[Unit]
Description=AIOS owner-controlled Task retry-extension API
After=aios-agent-task-api.service
Wants=aios-agent-task-api.service
[Service]
Type=simple
User=aios-agent-task
Group=aios-agent-task
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
EnvironmentFile=/etc/aios-gitops/agent-task-retry-extension.env
Environment=AIOS_AGENT_TASK_DB=/var/lib/aios-agent-task/state.sqlite3
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
Environment=AIOS_TASK_RETRY_HOST=127.0.0.1
Environment=AIOS_TASK_RETRY_PORT=18941
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_agent_task_retry_extension.py
Restart=on-failure
RestartSec=2
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
LockPersonality=true
RestrictSUIDSGID=true
RestrictRealtime=true
RestrictNamespaces=true
MemoryDenyWriteExecute=true
RestrictAddressFamilies=AF_UNIX AF_INET
ReadWritePaths=/var/lib/aios-agent-task
UMask=0077
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,33 @@
[Unit]
Description=AIOS uncredentialed deterministic Planner/Executor
After=local-fs.target
[Service]
Type=simple
User=aios-engineering-executor
Group=aios-executor-exchange
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_isolated_executor.py --root /var/lib/aios-online-agent-executor
Restart=always
RestartSec=2
NoNewPrivileges=true
PrivateTmp=true
PrivateNetwork=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
LockPersonality=true
RestrictSUIDSGID=true
RestrictRealtime=true
RestrictNamespaces=true
MemoryDenyWriteExecute=true
RestrictAddressFamilies=AF_UNIX AF_INET
IPAddressDeny=any
IPAddressAllow=localhost
InaccessiblePaths=/run/credentials
ReadWritePaths=/var/lib/aios-online-agent-executor
UMask=0027
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,46 @@
[Unit]
Description=AIOS governed Online Agent Worker
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
[Service]
Type=simple
User=aios-engineering-worker
Group=aios-engineering-worker
SupplementaryGroups=gitops aios-executor-exchange
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-online-agent-worker-20260815/agent_token
Environment=PYTHONUNBUFFERED=1
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
Environment=AIOS_AGENT_ID=online-engineering-worker
Environment=AIOS_AGENT_TYPE=trusted-online-engineering-worker
Environment=AIOS_AGENT_VERSION=2026-08-17.2-durable
Environment=AIOS_WORKER_CAPABILITIES=git.read,git.test,governed.write.branch,governed.write.file
Environment=AIOS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
Environment=AIOS_ISOLATED_EXECUTOR_ROOT=/var/lib/aios-online-agent-executor
Environment=AIOS_WORKER_STATE_ROOT=/var/lib/aios-online-agent-worker
Environment=AIOS_WORKER_CHECKPOINT_DB=/var/lib/aios-online-agent-worker/checkpoints.sqlite3
Environment=AIOS_WORKER_WORKSPACE_ROOT=/var/lib/aios-online-agent-worker/workspaces
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_online_agent_worker.py
Restart=always
RestartSec=5
TimeoutStopSec=20
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
LockPersonality=true
RestrictSUIDSGID=true
RestrictRealtime=true
RestrictNamespaces=true
MemoryDenyWriteExecute=true
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
ReadOnlyPaths=/data/aios-gitops/repo.git
ReadWritePaths=/var/lib/aios-online-agent-worker
UMask=0027
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,4 @@
g aios-executor-exchange -
u aios-engineering-executor - "AIOS isolated engineering executor" /var/lib/aios-online-agent-executor /usr/sbin/nologin
m aios-engineering-executor aios-executor-exchange
m aios-engineering-worker aios-executor-exchange
@@ -0,0 +1,5 @@
d /var/lib/aios-online-agent-executor 2770 aios-engineering-executor aios-executor-exchange -
d /var/lib/aios-online-agent-executor/requests 2770 aios-engineering-worker aios-executor-exchange -
d /var/lib/aios-online-agent-executor/results 2770 aios-engineering-executor aios-executor-exchange -
d /var/lib/aios-online-agent-executor/failed 2770 aios-engineering-executor aios-executor-exchange -
d /var/lib/aios-online-agent-executor/sources 2770 aios-engineering-worker aios-executor-exchange -
@@ -0,0 +1,75 @@
# R4.2 P1 — Durable Online Agent Execution
Status: candidate implementation. This document does not imply protected-main promotion or Production deployment.
## State model
The generic worker uses two local durable layers:
1. `tasks/<task_id>.json`: atomic fast-state cache for compatibility and quick restart.
2. `checkpoints.sqlite3`: append-only attempt/phase journal with `synchronous=FULL`.
Checkpoint identity is bound to:
- task_id
- attempt
- execution_digest
- job_id
- repository
- base_oid
- expected_branch_oid
- target_branch
- generation
A checkpoint from another repository/branch/generation is never reused.
Phases are monotonic within an attempt:
`claimed → workspace_prepared → verification_passed → source_capture_done|commit_done → result_pending → result_submitted`
`reconciliation_required` is an explicit recovery phase.
## Attempt-aware result idempotency
Result submission idempotency keys include the official Task attempt and the execution digest. The same
attempt reuses the same key after a timeout/restart; a later official attempt cannot collide with an
earlier result.
Before submitting a result the worker durably writes `result_pending`, including the result hash and
idempotency key. After a successful or exact-idempotency-reconciled API response it writes
`result_submitted`.
A 409 is accepted only if the Task API already contains the exact same result body and the Task is
VERIFYING/SUCCEEDED. A conflicting result remains a hard failure.
## Resume rules
- `source_capture_done` and `result_pending` may be reused across later official attempts only when the
execution/scope binding is identical. This avoids repeating read-only source capture.
- A deterministic task that crashed before governed commit replays from a new clean detached worktree.
This is safe because there is no external side effect yet.
- `commit_done` is never recommitted. Recovery requires exact Job receipt OID convergence plus exactly
one ACTIVE WriterLease whose `current_head_oid` equals the governed commit.
- delayed Git visibility remains `RECONCILIATION_REQUIRED`, preserving an explicit recovery entry.
## Crash cleanup
On worker startup, stale `task-*` workspaces under the configured workspace root are removed before
polling begins. The path boundary is verified before deletion.
## Contracts
P1 gates include:
- CHECKPOINT_DURABLE_WRITE
- RESUME_FROM_CHECKPOINT
- RETRY_IDEMPOTENT_NO_DUPLICATE_SIDE_EFFECT
- CRASH_RECOVERY_CONVERGENCE
- WORKER_RESTART_RESUME
- CHECKPOINT_SCOPE_ISOLATION
- RESULT_SUBMISSION_REPLAY_SAFE
- WORKSPACE_CLEANUP_RECOVERY
- LEASE_RENEWAL_RECOVERY
WriterLease and governed Job authority remain in the existing Bridge/GitOps durable stores; the worker
checkpoint DB is not a competing authority for Git state.
+117
View File
@@ -0,0 +1,117 @@
from pathlib import Path
import hashlib, json, sqlite3, sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
from aios_agent_task_retry_extension import RetryExtensionRequest, RetryExtensionStore, RetryExtensionError
AUTHORIZATION_ID="owner-scheme-a-20260817"
@pytest.fixture(autouse=True)
def _authorization_id(monkeypatch):
monkeypatch.setenv("AIOS_AGENT_TASK_AUTHORIZATION_ID", AUTHORIZATION_ID)
def canon(v):
return hashlib.sha256(json.dumps(v,sort_keys=True,separators=(",",":")).encode()).hexdigest()
def db(tmp_path):
p=tmp_path/"state.sqlite3"
c=sqlite3.connect(p)
c.executescript("""
CREATE TABLE tasks(
task_id TEXT PRIMARY KEY,status TEXT,attempt INTEGER,max_attempts INTEGER,revision INTEGER,
claimed_by TEXT,lease_token_hash TEXT,lease_expires_at TEXT,verification_json TEXT,result_json TEXT
);
CREATE TABLE task_events(
event_id INTEGER PRIMARY KEY AUTOINCREMENT,task_id TEXT,event_type TEXT,agent_id TEXT,
payload_json TEXT,created_at TEXT
);
""")
verification={"decision":"NEEDS_REWORK","reason":"BASE_OID_BINDING_INVALID"}
c.execute("INSERT INTO tasks VALUES (?,?,?,?,?,?,?,?,?,?)",
("task-a","FAILED",10,10,41,None,None,None,json.dumps(verification),json.dumps({"status":"FAILED"})))
c.commit(); c.close()
return p,verification
def request(v):
return RetryExtensionRequest.from_mapping({
"expected_status":"FAILED","expected_revision":41,"expected_attempt":10,"expected_max_attempts":10,
"next_max_attempts":11,"previous_verification_sha256":canon(v),
"authorization_id":AUTHORIZATION_ID,"idempotency_key":"retry-task-a-attempt11",
})
def test_retry_extension_cas_and_audit(tmp_path):
p,v=db(tmp_path)
out=RetryExtensionStore(p).extend("task-a",request(v))
assert out["status"]=="QUEUED" and out["max_attempts"]==11 and out["revision"]==42
c=sqlite3.connect(p)
assert c.execute("select status,attempt,max_attempts,revision from tasks").fetchone()==("QUEUED",10,11,42)
event=c.execute("select event_type,payload_json from task_events").fetchone()
assert event[0]=="TASK_RETRY_EXTENSION_AUTHORIZED"
assert json.loads(event[1])["authorization_id"]=="owner-scheme-a-20260817"
def test_retry_extension_idempotent_replay(tmp_path):
p,v=db(tmp_path); store=RetryExtensionStore(p); req=request(v)
first=store.extend("task-a",req); second=store.extend("task-a",req)
assert first["idempotent"] is False and second["idempotent"] is True
c=sqlite3.connect(p)
assert c.execute("select count(*) from task_retry_extensions").fetchone()[0]==1
def test_retry_extension_normalizes_stale_terminal_claim_without_active_lease(tmp_path):
p,v=db(tmp_path)
c=sqlite3.connect(p)
c.execute("update tasks set claimed_by='previous-worker'")
c.commit(); c.close()
out=RetryExtensionStore(p).extend("task-a",request(v))
assert out["status"]=="QUEUED"
c=sqlite3.connect(p)
assert c.execute(
"select claimed_by,lease_token_hash,lease_expires_at from tasks"
).fetchone()==(None,None,None)
payload=json.loads(c.execute("select payload_json from task_events").fetchone()[0])
assert payload["previous_claimed_by"]=="previous-worker"
assert payload["stale_terminal_claim_normalized"] is True
assert c.execute("select count(*) from task_events").fetchone()[0]==1
def test_retry_extension_verification_drift_denied(tmp_path):
p,v=db(tmp_path)
bad=request({"decision":"NEEDS_REWORK","reason":"other"})
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_VERIFICATION_DRIFT"):
RetryExtensionStore(p).extend("task-a",bad)
def test_retry_extension_authorization_id_mismatch_rejected(tmp_path, monkeypatch):
p,v=db(tmp_path)
monkeypatch.setenv("AIOS_AGENT_TASK_AUTHORIZATION_ID", "other-owner-id")
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_AUTHORIZATION_ID_MISMATCH"):
RetryExtensionStore(p).extend("task-a",request(v))
def test_retry_extension_bounded_one_step():
v={"decision":"NEEDS_REWORK"}
data={
"expected_status":"FAILED","expected_revision":41,"expected_attempt":10,"expected_max_attempts":10,
"next_max_attempts":12,"previous_verification_sha256":canon(v),
"authorization_id":"owner-scheme-a-20260817","idempotency_key":"retry-task-a-attempt11",
}
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_MUST_BE_BOUNDED_ONE_STEP"):
RetryExtensionRequest.from_mapping(data)
def test_retry_extension_unit_is_unprivileged_and_requires_owner_binding():
unit=(ROOT/"deploy/systemd/aios-agent-task-retry-extension.service").read_text()
assert "User=aios-agent-task" in unit
assert "Group=aios-agent-task" in unit
assert "LoadCredential=agent_task_control_token:" in unit
assert "EnvironmentFile=/etc/aios-gitops/agent-task-retry-extension.env" in unit
assert "User=root" not in unit
+67
View File
@@ -0,0 +1,67 @@
from pathlib import Path
import hashlib,json,os,tarfile,sys,tempfile
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
import aios_isolated_executor as mod
def make_archive(tmp_path):
root=tmp_path/"src"; root.mkdir()
(root/"hello.py").write_text("VALUE = 1\n")
archive=tmp_path/"source.tgz"
with tarfile.open(archive,"w:gz") as tf: tf.add(root/"hello.py",arcname="hello.py")
return archive
def test_isolated_executor_applies_hash_bound_change(tmp_path,monkeypatch):
archive=make_archive(tmp_path)
monkeypatch.delenv("CREDENTIALS_DIRECTORY",raising=False)
monkeypatch.setattr(mod,"assert_uncredentialed",lambda:None)
request={
"schema":"aios.isolated-execution.request.v1",
"request_id":"task-req-0000000000000000",
"source_archive":str(archive),
"source_archive_sha256":mod.sha256(archive.read_bytes()),
"change_set":[{
"path":"hello.py","operation":"replace_text","old":"VALUE = 1","new":"VALUE = 2","count":1,
"expected_sha256":mod.sha256(b"VALUE = 1\n")
}],
"verification":[{"label":"compile","argv":["/usr/bin/python3","-m","py_compile","hello.py"],"cwd":".","timeout_seconds":30}]
}
req=tmp_path/"req.json"; res=tmp_path/"res.json"
req.write_text(json.dumps(request))
mod.execute_request(req,res)
out=json.loads(res.read_text())
assert out["request_id"]=="task-req-0000000000000000"
assert out["credential_isolation"]["credential_env_absent"] is True
changed=out["changed_files"][0]
assert changed["path"]=="hello.py" and changed["deleted"] is False
def test_isolated_executor_source_drift_denied(tmp_path,monkeypatch):
archive=make_archive(tmp_path); monkeypatch.setattr(mod,"assert_uncredentialed",lambda:None)
request={
"schema":"aios.isolated-execution.request.v1","request_id":"task-req-0000000000000001",
"source_archive":str(archive),
"source_archive_sha256":mod.sha256(archive.read_bytes()),
"change_set":[{"path":"hello.py","operation":"write_file","content":"x\n","expected_sha256":"0"*64}],
"verification":[]
}
req=tmp_path/"req.json"; res=tmp_path/"res.json"; req.write_text(json.dumps(request))
with pytest.raises(mod.IsolatedExecutorError,match="SOURCE_DRIFT"):
mod.execute_request(req,res)
def test_credential_boundary_eacces_is_accepted(monkeypatch):
class DeniedDirectory:
def exists(self): return True
def is_symlink(self): return False
def is_dir(self): return True
def iterdir(self): raise PermissionError(13,"permission denied")
monkeypatch.setattr(mod.os,"access",lambda *_args,**_kwargs:False)
assert mod._credential_exposure(DeniedDirectory()) is None
def test_systemd_unit_has_no_credentials_and_private_network():
unit=(ROOT/"deploy/systemd/aios-online-agent-isolated-executor.service").read_text()
assert "PrivateNetwork=true" in unit
assert "InaccessiblePaths=/run/credentials" in unit
assert "LoadCredential" not in unit
assert "SupplementaryGroups=gitops" not in unit
@@ -0,0 +1,216 @@
from __future__ import annotations
from pathlib import Path
import json
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
APP=ROOT/"active-runtime/app"
sys.path.insert(0,str(APP))
from aios_online_agent_checkpoint import (
CheckpointBinding,
CheckpointError,
CheckpointStore,
)
import aios_online_agent_worker as worker
def binding(attempt: int = 1, *, tenant_head: str = "b"*40):
return CheckpointBinding(
task_id="task-p1-a",
attempt=attempt,
execution_digest="d"*64,
job_id="job-p1-a",
repository="aios/aios",
base_oid="a"*40,
expected_branch_oid=tenant_head,
target_branch="agent/task-p1-a",
generation=1,
)
def test_CHECKPOINT_DURABLE_WRITE(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
first=store.append(binding(), "claimed", {"phase":"claimed","attempt":1})
second=store.append(binding(), "workspace_prepared", {"phase":"workspace_prepared","attempt":1})
assert first["sequence"] == 1
assert second["sequence"] == 2
latest=store.latest("task-p1-a")
assert latest["phase"]=="workspace_prepared"
assert latest["payload"]["attempt"]==1
def test_CHECKPOINT_SCOPE_ISOLATION(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(), "claimed", {"phase":"claimed"})
changed=CheckpointBinding(
task_id="task-p1-a",attempt=1,execution_digest="d"*64,job_id="job-p1-a",
repository="aios/other",base_oid="a"*40,expected_branch_oid="b"*40,
target_branch="agent/task-p1-a",generation=1,
)
with pytest.raises(CheckpointError,match="CHECKPOINT_SCOPE_MISMATCH_DENY"):
store.append(changed,"workspace_prepared",{"phase":"workspace_prepared"})
def test_RESUME_FROM_CHECKPOINT_across_attempt_same_binding(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(1), "source_capture_done", {
"phase":"source_capture_done",
"attempt":1,
"result":{"status":"SUCCEEDED","classification":"NEEDS_REWORK_SOURCE_CAPTURE"},
})
resumed=store.verify_latest_binding(binding(2))
assert resumed is not None
assert resumed["attempt"]==1
assert resumed["phase"]=="source_capture_done"
def test_checkpoint_new_attempt_can_start_from_claimed(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(1),"result_submitted",{"phase":"result_submitted"})
cp=store.append(binding(2),"claimed",{"phase":"claimed"})
assert cp["attempt"]==2
assert cp["sequence"]==1
def envelope():
return worker.ExecutionEnvelope(
task_id="task-p1-a",
job_id="job-p1-a",
repository="aios/aios",
base_oid="a"*40,
expected_branch_oid="b"*40,
target_branch="agent/task-p1-a",
branch_mode="CONTINUE_EXISTING",
generation=1,
idempotency_key="governed-p1-a",
action="source_capture",
adapter="source_capture",
capability_scope=("git.read","git.test"),
source_signals=(),
change_set=(),
verification=(),
governance={"task_id":"task-p1-a","job_id":"job-p1-a"},
workspace={},
digest="d"*64,
)
def test_RESULT_SUBMISSION_REPLAY_SAFE_attempt_aware_key():
env=envelope()
result={"status":"SUCCEEDED","execution_digest":env.digest}
one=worker.result_idempotency_key(env.task_id,1,env,result)
two=worker.result_idempotency_key(env.task_id,2,env,result)
assert one != two
assert "-a1-result-" in one
assert "-a2-result-" in two
assert one == worker.result_idempotency_key(env.task_id,1,env,result)
class RetryClient:
def __init__(self):
self.calls=[]
def result(self,task_id,lease_token,key,result):
self.calls.append((task_id,key,dict(result)))
return (599,{"error":"SERVICE_UNAVAILABLE"}) if len(self.calls)==1 else (201,{"status":"VERIFYING"})
def get(self,task_id):
return 500,{}
def test_RETRY_IDEMPOTENT_NO_DUPLICATE_SIDE_EFFECT_reuses_same_key(monkeypatch):
client=RetryClient()
monkeypatch.setattr(worker.time,"sleep",lambda _:None)
status,response=worker.submit_result_replay_safe(
client,"task-p1-a","lease-token-"+"x"*32,"stable-key",{"status":"SUCCEEDED"}
)
assert status==201
assert [item[1] for item in client.calls]==["stable-key","stable-key"]
class ConflictClient:
def __init__(self,result):
self.result_value=result
def result(self,*args):
return 409,{"error":"IDEMPOTENCY_CONFLICT"}
def get(self,task_id):
return 200,{"status":"VERIFYING","result":dict(self.result_value)}
def test_RESULT_SUBMISSION_REPLAY_SAFE_reconciles_exact_result():
result={"status":"SUCCEEDED","value":1}
status,response=worker.submit_result_replay_safe(
ConflictClient(result),"task-p1-a","lease-token-"+"x"*32,"stable-key",result
)
assert status==200
assert response["idempotent"] is True
assert response["reconciled"] is True
def test_RESULT_SUBMISSION_REPLAY_SAFE_rejects_conflicting_result():
status,response=worker.submit_result_replay_safe(
ConflictClient({"status":"SUCCEEDED","value":2}),
"task-p1-a","lease-token-"+"x"*32,"stable-key",
{"status":"SUCCEEDED","value":1},
)
assert status==409
assert response["error"]=="IDEMPOTENCY_CONFLICT"
def test_WORKSPACE_CLEANUP_RECOVERY(tmp_path,monkeypatch):
root=tmp_path/"workspaces"; root.mkdir()
stale=root/"task-old"; stale.mkdir(); (stale/"x").write_text("x")
monkeypatch.setattr(worker,"WORKSPACE_ROOT",root)
monkeypatch.setattr(worker,"STATE_ROOT",tmp_path/"state")
removed=worker.recover_stale_workspaces()
assert removed==1
assert not stale.exists()
class LeaseBridge:
def __init__(self):
self.calls=0
def call(self,route,body):
assert route=="/v2/writer-lease"
self.calls+=1
if self.calls==1:
return 599,{"error":"SERVICE_UNAVAILABLE"}
return 200,{
"lease_id":"lease-p1-a",
"job_id":"job-p1-a",
"task_id":"task-p1-a",
"repository":"aios/aios",
"base_oid":"a"*40,
"expected_branch_oid":"b"*40,
"branch_mode":"CONTINUE_EXISTING",
"generation":1,
"target_branch":"agent/task-p1-a",
"state":"ACTIVE",
}
class LeaseHeartbeatStub:
def ensure(self):
return None
def test_LEASE_RENEWAL_RECOVERY_retries_same_binding(monkeypatch):
env=envelope()
env=worker.ExecutionEnvelope(
task_id=env.task_id,job_id=env.job_id,repository=env.repository,
base_oid=env.base_oid,expected_branch_oid=env.expected_branch_oid,
target_branch=env.target_branch,branch_mode=env.branch_mode,generation=env.generation,
idempotency_key=env.idempotency_key,action=env.action,adapter=env.adapter,
capability_scope=env.capability_scope,source_signals=env.source_signals,
change_set=env.change_set,verification=env.verification,
governance={"task_id":env.task_id,"job_id":env.job_id,"lease_seconds":900},
workspace=env.workspace,digest=env.digest,
)
bridge=LeaseBridge()
monkeypatch.setattr(worker.time,"sleep",lambda _:None)
monkeypatch.setattr(worker,"STATE_ROOT",Path("/tmp")/"aios-p1-test-state")
response=worker.acquire_writer_lease_replay_safe(env,bridge,LeaseHeartbeatStub())
assert response["lease_id"]=="lease-p1-a"
assert bridge.calls==2
+60
View File
@@ -0,0 +1,60 @@
from pathlib import Path
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
from aios_online_agent_execution import GovernedExecutionBinding
from aios_online_agent_plan_store import ExecutionPlanStore, ExecutionPlanError
BASE="a642b045775b9154a00ae78543037fbef4fb447b"
HEAD="71523aef6e48b1e2fa516c456ca189b7a039104b"
def binding(head=HEAD):
return GovernedExecutionBinding.from_mapping({
"task_id":"task-plan-a","job_id":"job-plan-a","repository":"aios/aios","base_oid":BASE,
"expected_branch_oid":head,"target_branch":"agent/task-plan-a","branch_mode":"CONTINUE_EXISTING",
"generation":1,"idempotency_key":"governed-plan-a",
})
def request():
return {
"schema":"aios.online-agent.plan.v1","task_id":"task-plan-a","job_id":"job-plan-a",
"source_head_oid":HEAD,"generation":1,"idempotency_key":"plan-task-a-v1",
"execution":{
"action":"deterministic",
"change_set":[{"path":"x.py","operation":"write_file","content":"x=1\n"}],
"verification":[{"label":"compile","argv":["/usr/bin/python3","-m","py_compile","x.py"],"cwd":".","timeout_seconds":30}],
"capability_scope":["git.read","git.test"],
}
}
def test_plan_register_and_resolve(tmp_path):
store=ExecutionPlanStore(tmp_path)
created=store.register(binding(),request())
assert created["idempotent"] is False
resolved=store.resolve(binding())
assert resolved["plan_digest"]==created["plan_digest"]
assert resolved["execution"]["action"]=="deterministic"
def test_plan_is_idempotent(tmp_path):
store=ExecutionPlanStore(tmp_path); req=request()
first=store.register(binding(),req); second=store.register(binding(),req)
assert second["idempotent"] is True
assert first["plan_digest"]==second["plan_digest"]
def test_plan_source_head_drift_denied(tmp_path):
store=ExecutionPlanStore(tmp_path); store.register(binding(),request())
with pytest.raises(ExecutionPlanError,match="SOURCE_HEAD_DRIFT"):
store.resolve(binding("b"*40))
def test_plan_replacement_requires_cas(tmp_path):
store=ExecutionPlanStore(tmp_path); first=store.register(binding(),request())
changed=request(); changed["idempotency_key"]="plan-task-a-v2"
changed["execution"]["change_set"][0]["content"]="x=2\n"
with pytest.raises(ExecutionPlanError,match="REPLACEMENT_CAS_MISMATCH"):
store.register(binding(),changed)
changed["expected_previous_plan_digest"]=first["plan_digest"]
second=store.register(binding(),changed)
assert second["plan_digest"]!=first["plan_digest"]